Ling 3.0 Flash Fin
Neural Network
Ling 3.0 Flash Fin is an InclusionAI MoE model for financial analysis, available via API in BotHub.
Specifications
- Input
- text, documents
- Output
- text
- Context size
- 262 144 tokens
- Max answer length
- 32 768 tokens
- Reasoning effort
- low, medium, high
- Capabilities
- reasoning, function calling
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: '<your bothub access token>',
baseURL: 'https://openai.bothub.chat/v1'
});
// Sync - Text generation
async function main() {
const chatCompletion = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'ling-3.0-flash-fin',
});
}
// Async - Text generation
async function main() {
const stream = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'ling-3.0-flash-fin',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works Ling 3.0 Flash Fin?
Ling 3.0 Flash Fin is a specialized model from InclusionAI, built on Ling 3.0 Flash and tailored for the financial domain. It uses a mixture-of-experts architecture: out of 124B parameters, about 5.1B are activated per request, keeping the model efficient while retaining large-network capacity. The main difference from the base Ling 3.0 Flash is its focus on applied investment scenarios. Via BotHub, the model is accessible from Russia without a VPN or foreign card; payment is in rubles, and purchased tokens do not expire. Over 250 models are available in the same window, and you can switch between them without rewriting your integration using the unified OpenAI-compatible API. Dialogues are protected by AES-GCM encryption, and companies have access to contracts, invoices, electronic document management, and an admin panel with limits. Analysts can use the model to parse issuer reports and summarize key metrics, investment consultants to prepare investment ideas, product teams to integrate a financial assistant via API, and developers to run batches of market data queries.Frequently asked questions about Ling 3.0 Flash Fin
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
ling-3.0-flash-fin is a text model from inclusionai. A context window of up to 262,144 tokens allows you to upload large documents and get analysis, summaries, or precise answers. It is suitable for analytics, coding, STEM reasoning, and scenarios requiring external tool calls.
The output limit is 235,929 tokens per response, meaning the model can generate very long text without cutting off. This is sufficient for large reports, detailed documentation, long translations, or large code fragments in their entirety, without manual assembly.
Yes, reasoning before answering is a supported capability. It breaks down the problem step-by-step before formulating the result, which helps with calculations, multi-step logic, resolving conflicting requirements, and code debugging where the sequence of actions is critical.
Yes, the model supports function calling and structured JSON output. You define the schema, receive a predictable response, and pass it to your code. Connection is via the unified OpenAI-compatible BotHub API, so you can switch models without rewriting your integration.
According to our data, text and documents are confirmed inputs: you can upload a file and work with its content. Image, audio, or video input is not indicated in the card, so for such materials, it is better to choose a multimodal model—they are available in the same BotHub window.
We have no data on its performance with Russian, so we cannot guarantee accuracy. Test it with your own tasks: open the model in BotHub, send a typical request, and compare it with other options in the same window. Access from Russia without a VPN or foreign card.